Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement

TL;DR

This paper introduces an uncertainty-aware GAN framework with an adaptive loss function that enhances robustness to out-of-distribution noisy data and provides voxel-level uncertainty quantification in medical MRI image enhancement tasks.

Contribution

The proposed method uniquely combines adaptive loss modeling with uncertainty estimation in GANs for improved robustness and interpretability in medical imaging.

Findings

Robustness to OOD-noisy MRI data demonstrated

Improved accuracy in MRI reconstruction and modality propagation

Effective voxel-level uncertainty quantification

Abstract

Image-to-image translation is an ill-posed problem as unique one-to-one mapping may not exist between the source and target images. Learning-based methods proposed in this context often evaluate the performance on test data that is similar to the training data, which may be impractical. This demands robust methods that can quantify uncertainty in the prediction for making informed decisions, especially for critical areas such as medical imaging. Recent works that employ conditional generative adversarial networks (GANs) have shown improved performance in learning photo-realistic image-to-image mappings between the source and the target images. However, these methods do not focus on (i)~robustness of the models to out-of-distribution (OOD)-noisy data and (ii)~uncertainty quantification. This paper proposes a GAN-based framework that (i)~models an adaptive loss function for robustness to OOD-noisy data that automatically tunes the spatially varying norm for penalizing the residuals and (ii)~estimates the per-voxel uncertainty in the predictions. We demonstrate our method on two key applications in medical imaging: (i)~undersampled magnetic resonance imaging (MRI) reconstruction (ii)~MRI modality propagation. Our experiments with two different real-world datasets show that the proposed method (i)~is robust to OOD-noisy test data and provides improved accuracy and (ii)~quantifies voxel-level uncertainty in the predictions.